Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Neon, the No. 2 social app on the Apple App Store, pays users to record their phone calls and sells data to AI firms

Canadian A.I. Startup Cohere Valued at $7B After Raising Another $100M

Perplexity Comet AI web browser launches in India with a catch: Check how to download, setup and more – Technology News

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Business AI
    • Advanced AI News Features
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Hugging Face

Reinforcement Learning on Pre-Training Data – Takara TLDR

By Advanced AI EditorSeptember 24, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email


The growing disparity between the exponential scaling of computational
resources and the finite growth of high-quality text data now constrains
conventional scaling approaches for large language models (LLMs). To address
this challenge, we introduce Reinforcement Learning on Pre-Training data
(RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast
to prior approaches that scale training primarily through supervised learning,
RLPT enables the policy to autonomously explore meaningful trajectories to
learn from pre-training data and improve its capability through reinforcement
learning (RL). While existing RL strategies such as reinforcement learning from
human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR)
rely on human annotation for reward construction, RLPT eliminates this
dependency by deriving reward signals directly from pre-training data.
Specifically, it adopts a next-segment reasoning objective, rewarding the
policy for accurately predicting subsequent text segments conditioned on the
preceding context. This formulation allows RL to be scaled on pre-training
data, encouraging the exploration of richer trajectories across broader
contexts and thereby fostering more generalizable reasoning skills. Extensive
experiments on both general-domain and mathematical reasoning benchmarks across
multiple models validate the effectiveness of RLPT. For example, when applied
to Qwen3-4B-Base, RLPT yields absolute improvements of $3.0$, $5.1$, $8.1$,
$6.0$, $6.6$, and $5.3$ on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and
AIME25, respectively. The results further demonstrate favorable scaling
behavior, suggesting strong potential for continued gains with more compute. In
addition, RLPT provides a solid foundation, extending the reasoning boundaries
of LLMs and enhancing RLVR performance.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleHow Qwen 3 Omni is Transforming AI with Multimodal Mastery
Next Article C3 AI Named a Leader in Industrial AI
Advanced AI Editor
  • Website

Related Posts

Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications – Takara TLDR

September 24, 2025

DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models’ Understanding on Indian Culture – Takara TLDR

September 24, 2025

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT – Takara TLDR

September 24, 2025

Comments are closed.

Latest Posts

Art Dealer Mary Boone Says Prison Was ‘Very Relaxing’

New Research Supports Theory of Hidden Vermeer Self-Portrait

John Singer Sargent Paintings Expected to Bring In $12-15 Million

John Giorno’s Decades-Long Project Dial-A-Poem Is Now Online

Latest Posts

Neon, the No. 2 social app on the Apple App Store, pays users to record their phone calls and sells data to AI firms

September 24, 2025

Canadian A.I. Startup Cohere Valued at $7B After Raising Another $100M

September 24, 2025

Perplexity Comet AI web browser launches in India with a catch: Check how to download, setup and more – Technology News

September 24, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Neon, the No. 2 social app on the Apple App Store, pays users to record their phone calls and sells data to AI firms
  • Canadian A.I. Startup Cohere Valued at $7B After Raising Another $100M
  • Perplexity Comet AI web browser launches in India with a catch: Check how to download, setup and more – Technology News
  • Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications – Takara TLDR
  • Microsoft incorporates Anthropic’s Claude AI into 365 Copilot

Recent Comments

  1. JohnnieGuh on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  2. Michaelsex on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. typiseThymn on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  4. Rodneycrync on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  5. Ismaelzek on Former Sotheby’s Vet Launches Art Lending Firm with Nahmads’ Backing

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.